clip-search: offset-based pagination on /photos/search

Adds `offset` query param (default 0) and `total_matching` + `offset`
response fields. Backend already computes the full sorted list of
above-threshold matches per query; pagination just slices it at
[offset, offset+limit) instead of always returning the top window.
Offsets past the end return an empty page cleanly so the client can
stop fetching naturally.

Re-scores on every page rather than caching the sorted list — at
personal-library scale (~14k embeddings, 768d) the dot-product loop
is sub-100ms and the lack of state means no eviction / staleness
concerns.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/clip_search.rs

@@ -33,10 +33,16 @@ use std::sync::Mutex;
 pub struct SearchQuery {
     /// Natural-language query. Required; empty triggers 400.
     pub q: String,
-    /// Max results to return. Capped to 200 server-side; the UI almost
+    /// Max results to return in this page. Capped to 200 server-side.
-    /// always wants ≤50. Defaults to 20.
+    /// Defaults to 20. Pair with `offset` for pagination.
     #[serde(default = "default_limit")]
     pub limit: usize,
+    /// Zero-based offset into the sorted-and-filtered result set. The
+    /// scoring loop still runs over the full embedding matrix on every
+    /// page (cheap at personal-library scale — sub-100ms — and avoids
+    /// stateful pagination cursors). Defaults to 0.
+    #[serde(default)]
+    pub offset: usize,
     /// Cosine-similarity floor below which results are dropped.
     /// 0.20 is the rough "this is plausibly relevant" line for OpenAI
     /// CLIP; tunable per call when sweeping. Defaults to 0.20.
@@ -76,7 +82,14 @@ pub struct SearchResponse {
     pub query: String,
     pub model_version: String,
     pub threshold: f32,
+    /// Total embeddings scored (= every photo in scope with a stored
+    /// embedding). Same value across pages of the same query.
     pub considered: usize,
+    /// Count of results above threshold, before pagination. Lets the
+    /// client decide whether a "Load more" button is meaningful and
+    /// stop fetching when ``offset + results.len() >= total_matching``.
+    pub total_matching: usize,
+    pub offset: usize,
     pub results: Vec<SearchHit>,
 }
 
@@ -122,6 +135,7 @@ pub async fn search_photos(
     }
 
     let limit = query.limit.clamp(1, 200);
+    let offset = query.offset;
     let threshold = query.threshold.clamp(-1.0, 1.0);
 
     // 1. Encode the query text. Fast — Apollo's text encoder is ~50ms
@@ -195,6 +209,8 @@ pub async fn search_photos(
             model_version: query_resp.model_version,
             threshold,
             considered,
+            total_matching: 0,
+            offset,
             results: Vec::new(),
         }));
     }
@@ -216,7 +232,16 @@ pub async fn search_photos(
         scored.push((sim, hash));
     }
     scored.sort_by(|a, b| b.0.partial_cmp(&a.0).unwrap_or(std::cmp::Ordering::Equal));
-    scored.truncate(limit);
+    let total_matching = scored.len();
+    // Pagination — slice the sorted list at `[offset, offset+limit)`.
+    // Offsets past the end produce empty pages rather than an error so
+    // the client can stop fetching naturally on "load more" past the end.
+    let scored: Vec<(f32, String)> = if offset >= total_matching {
+        Vec::new()
+    } else {
+        let end = (offset + limit).min(total_matching);
+        scored[offset..end].to_vec()
+    };
 
     if scored.is_empty() {
         return Ok(HttpResponse::Ok().json(SearchResponse {
@@ -224,6 +249,8 @@ pub async fn search_photos(
             model_version: query_resp.model_version,
             threshold,
             considered,
+            total_matching,
+            offset,
             results: Vec::new(),
         }));
     }
@@ -287,6 +314,8 @@ pub async fn search_photos(
         model_version: query_resp.model_version,
         threshold,
         considered,
+        total_matching,
+        offset,
         results,
     }))
 }